BitsExplorer

BitsExplorer finds what people are building with AI, every day. See today's picks →

Preview of FastLocalExperts

FastLocalExperts

FLE - Fast Local Experts: a llama.cpp fork that runs Qwen3.8-Flash-Next (89 GB MoE) at about 90 tokens/s on one 32 GB GPU

Description excerpted from the original listing, which is linked below.

Open it Source code

The week in AI-built software

Every Monday: how many projects were built with AI that week, which tools built them, where they came from, and the week's picks.

Read the latest week